## Libraries
import pandas as pd
import numpy as np

from sklearn.model_selection import train_test_split, StratifiedShuffleSplit
from sklearn.preprocessing import LabelEncoder
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler, OneHotEncoder
from sklearn.compose import ColumnTransformer
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_absolute_error, r2_score 
from sklearn.model_selection import RandomizedSearchCV

import seaborn as sns
import matplotlib.pyplot as plt

import plotly.express as px
import plotly.io as pio
import plotly.offline as pyo
pio.renderers.default = "iframe"
pio.templates.default = "plotly_dark"  
pio.renderers.default = 'notebook_connected'

house_rent = pd.read_csv("Project_data.csv")

house_rent.head()

house_rent.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 17890 entries, 0 to 17889
Data columns (total 15 columns):
 #   Column                    Non-Null Count  Dtype  
---  ------                    --------------  -----  
 0   Column1                   17890 non-null  int64  
 1   size_sq_ft                17890 non-null  int64  
 2   propertyType              17890 non-null  object 
 3   bedrooms                  17890 non-null  int64  
 4   latitude                  17890 non-null  float64
 5   longitude                 17890 non-null  float64
 6   localityName              17890 non-null  object 
 7   suburbName                17890 non-null  object 
 8   cityName                  17890 non-null  object 
 9   price                     17890 non-null  int64  
 10  companyName               17890 non-null  object 
 11  closest_mtero_station_km  17890 non-null  float64
 12  AP_dist_km                17890 non-null  float64
 13  Aiims_dist_km             17890 non-null  float64
 14  NDRLW_dist_km             17890 non-null  float64
dtypes: float64(6), int64(4), object(5)
memory usage: 2.0+ MB

house_rent.describe()

df = house_rent.duplicated()
df.value_counts()

False    17890
Name: count, dtype: int64

print(f"We have {house_rent['companyName'].unique().shape} company")
print(f"Our dataset based only {house_rent['cityName'].unique().shape} City")

We have (1387,) company
Our dataset based only (1,) City

print(f"We have {house_rent['localityName'].unique().shape}Locality")

We have (781,)Locality

house_rent['suburbName'].unique()

array(['Delhi East', 'Rohini', 'Delhi South', 'West Delhi', 'North Delhi',
       'Dwarka', 'Delhi Central', 'Other', 'South West Delhi',
       'Delhi North', 'North West Delhi', 'Delhi West'], dtype=object)

print("This table shows the average asking price for each suburb area.")
house_rent.groupby('suburbName')['price'].mean().sort_values()

This table shows the average asking price for each suburb area.

suburbName
South West Delhi    16848.697674
Delhi East          17650.752199
West Delhi          23735.962646
Rohini              23820.437956
North West Delhi    24254.545455
Dwarka              28285.025051
Delhi North         29045.454545
Delhi West          29620.156051
North Delhi         30469.256390
Other               35485.701774
Delhi Central       35606.693997
Delhi South         50311.178448
Name: price, dtype: float64

house_rent['suburbName'] = house_rent['suburbName'].replace('Delhi North','North Delhi')
house_rent['suburbName'] = house_rent['suburbName'].replace('Delhi West','West Delhi')
house_rent['suburbName'] = house_rent['suburbName'].replace('Rohini','North West Delhi')
house_rent['suburbName'] = house_rent['suburbName'].replace('Dwarka','South West Delhi')
house_rent['suburbName'] = house_rent['suburbName'].replace('Delhi South','South Delhi')
house_rent['suburbName'] = house_rent['suburbName'].replace('Delhi East','East Delhi')

other_suburbs = house_rent[house_rent['suburbName'].str.contains("^Other", na=False)]

# 1. Define mapping from localityName to suburbName
locality_to_suburb = {
    'laxmi nagar': 'East Delhi',
    'sultanpur': 'South Delhi',
    'chittaranjan park': 'South Delhi',
    'kirari suleman nagar': 'North West Delhi',
    'khirki extension': 'South Delhi',
    'khirki extension panchsheel vihar': 'South Delhi',
    'mansa ram park': 'South West Delhi',
    'govindpuri': 'South Delhi',
    'govindpuri Main': 'South Delhi',
    'pitampura': 'North West Delhi',
    'rajdhani enclave': 'North West Delhi',
    'vikaspuri':'West Delhi',
    'west end' : 'South Delhi',
    'new rajendra nagar':'Delhi Central'
}

# 2. Convert localityName to lowercase to ensure case-insensitive matching
house_rent['localityName_clean'] = house_rent['localityName'].str.lower().str.strip()

# 3. Fill suburbName based on the mapping
house_rent['suburbName'] = house_rent.apply(
    lambda row: locality_to_suburb[row['localityName_clean']]
    if row['localityName_clean'] in locality_to_suburb else row['suburbName'],
    axis=1
)

# Filter rows where suburbName is 'Other Area' or contains 'Other'
other_mask = house_rent['suburbName'].str.lower().str.contains('other', na=False)

# Count how many times each locality appears in these rows
locality_freq_in_other = house_rent[other_mask]['localityName'].value_counts()

# Display result
print(locality_freq_in_other.head(20))

localityName
Poorvi Pitampura                                 71
Sector-7 Rohini                                  65
Sector-18 Dwarka                                 54
Prashant Vihar Sector 14                         41
Rohini Sector 9                                  40
Uttari Pitampura                                 32
Jangpura Extension                               30
Neeti Bagh                                       29
South Extension Part 1                           28
Sector 6 Rohini                                  24
DLF Phase 5                                      22
Dr Mukherjee Nagar West Bhai Parmanand Colony    17
Abul Fazal Enclave Jamia Nagar                   17
Jawahar Park                                     17
Khanpur Krishna Park                             17
Sant Nagar                                       16
Bharat Vihar                                     16
Sector 15 Rohini                                 16
Paschim Vihar A 1 Block                          16
Bank Enclave                                     16
Name: count, dtype: int64

locality_to_suburb = {
    'jawahar park': 'South Delhi',
    'khanpur krishna park': 'South Delhi',
    'dr mukherjee nagar west bhai parmanand colony': 'North Delhi',
    'jangpura extension': 'South Delhi',
    'abul fazal enclave jamia nagar': 'South Delhi',
    'sant nagar': 'South Delhi',
    'bharat vihar': 'West Delhi',
    'gtb nagar': 'North Delhi',
    'saidabad': 'East Delhi',
    'raju park': 'South Delhi',
    'jasola vihar sector 8 road': 'South Delhi',
    'chhattarpur enclave phase1': 'South Delhi',
    'mangal bazar road': 'Delhi Central',
    'jamia nagar': 'South Delhi',
    'aya nagar': 'South Delhi',
    'mayur vihar phase 2': 'East Delhi',
    'mayur vihar phase 3': 'East Delhi',
    'amar colony': 'South Delhi'
}

house_rent['localityName_clean'] = house_rent['localityName'].str.lower().str.strip()

house_rent['suburbName'] = house_rent.apply(
    lambda row: locality_to_suburb[row['localityName_clean']]
    if row['localityName_clean'] in locality_to_suburb else row['suburbName'],
    axis=1
)

# Convert locality name to lowercase for safe matching
house_rent['localityName_clean'] = house_rent['localityName'].str.lower().str.strip()
# Corrected: Use lowercase strings in .str.contains()
house_rent.loc[house_rent['localityName_clean'].str.contains('rohini', na=False), 'suburbName'] = 'North West Delhi'
house_rent.loc[house_rent['localityName_clean'].str.contains('pitampura', na=False), 'suburbName'] = 'North West Delhi'
house_rent.loc[house_rent['localityName_clean'].str.contains('prashant', na=False), 'suburbName'] = 'North West Delhi'
house_rent.loc[house_rent['localityName_clean'].str.contains('chattarpur', na=False), 'suburbName'] = 'South Delhi'
house_rent.loc[house_rent['localityName_clean'].str.contains('dwarka', na=False), 'suburbName'] = 'South West Delhi'
house_rent.loc[house_rent['localityName_clean'].str.contains('paschim vihar', na=False), 'suburbName'] = 'West Delhi'
house_rent.loc[house_rent['localityName_clean'].str.contains('punjabhi bagh', na=False), 'suburbName'] = 'West Delhi'

# this is the corrected table of mean price by suburb area
house_rent.groupby('suburbName')['price'].mean().sort_values()

suburbName
East Delhi          16853.991714
West Delhi          25484.500220
South West Delhi    26965.963132
North West Delhi    27532.220395
North Delhi         28306.407756
Delhi Central       35544.416035
South Delhi         46637.124554
Other               60501.648364
Name: price, dtype: float64

# Using boxplot to detect outliers
plt.figure(figsize=(15, 6))  
fig = sns.boxplot(data=house_rent)

plt.xticks(rotation=45) 
plt.title("Boxplot of House Rent Dataset")
plt.show()

q1 = house_rent['price'].quantile(0.25)
q3 = house_rent['price'].quantile(0.75)

IQR = q3-q1

house_rent = house_rent[(house_rent['price']>=q1-1.5*IQR)&
                        (house_rent['price']<=q3+1.5*IQR)]

plt.figure(figsize=(15, 6))  # Increase width
fig = sns.boxplot(data=house_rent)

plt.xticks(rotation=45)  # Rotate x-axis labels for better visibility
plt.title("Boxplot of House Rent Dataset")
plt.show()

house_rent = house_rent[house_rent["price"]<=55000]

fig = sns.boxplot(house_rent["price"])
fig

<Axes: ylabel='price'>

house_rent = house_rent[house_rent["size_sq_ft"]<=2400]

fig = sns.boxplot(house_rent["size_sq_ft"])
fig

<Axes: ylabel='size_sq_ft'>

house_rent = house_rent[house_rent["longitude"] <= 77.39103]
house_rent = house_rent[house_rent["longitude"] >= 76.95978]

le = LabelEncoder()
house_rent['locality_encoded'] = le.fit_transform(house_rent['localityName_clean'])

locality_price_mean = house_rent.groupby('localityName_clean')['price'].mean()
house_rent['locality_encoded'] = house_rent['localityName_clean'].map(locality_price_mean)

house_rent['suburbName_clean'] = house_rent['suburbName'].str.lower().str.strip()

# drop unneccessary features
house_rent = house_rent.drop("Column1",axis=1)
house_rent = house_rent.drop("suburbName",axis=1)
house_rent = house_rent.drop("localityName",axis=1)
house_rent = house_rent.drop("companyName",axis=1)
house_rent = house_rent.drop("closest_mtero_station_km",axis=1)
house_rent = house_rent.drop("Aiims_dist_km",axis=1)
house_rent = house_rent.drop("NDRLW_dist_km",axis=1)

house_rent.head()

housing_num = house_rent.drop(["propertyType","suburbName_clean",'localityName_clean','cityName'] ,axis=1)

original_count = 17890
cleaned_count = len(house_rent)

rows_dropped = original_count - cleaned_count
percentage_lost = (rows_dropped / original_count) * 100

print(f"Rows dropped: {rows_dropped} ({percentage_lost:.2f}%)")

Rows dropped: 1986 (11.10%)

corr_matrix = housing_num.corr()
plt.figure(figsize=(10, 6))
sns.heatmap(corr_matrix, annot=True, cmap="coolwarm", fmt=".2f", linewidths=0.5)

plt.title("Correlation Heatmap")
plt.show()

corr_matrix["price"].sort_values(ascending=False)

price               1.000000
size_sq_ft          0.766358
locality_encoded    0.669048
bedrooms            0.665165
latitude            0.016233
longitude          -0.162069
AP_dist_km         -0.182466
Name: price, dtype: float64

#  Overall Feature Distributions
%matplotlib inline
house_rent.hist(bins=50, figsize=(20,15))
plt.show()

# Price Distribution of Houses
import plotly.io as pio

fig = px.histogram(house_rent ,x = "price")

fig.update_layout(
    title = "Price Range",
    title_x = 0.5,
    xaxis_title = "Price",
    yaxis_title  = "No. of House",
    font = dict(size= 16)
)

fig.update_traces (
    hovertemplate ='<b>Price range of house:</b> %{x}<br><b>No.of house:</b> %{y}'
)
fig.show()

# Distribution of Property Types
import plotly.io as pio
propertyType = house_rent["propertyType"].value_counts().reset_index()
propertyType.columns = ['Property Type', 'count']

fig = px.bar(
    propertyType, 
    x='Property Type',
    y='count' ,
    color_discrete_sequence=['orange'], 
    title="Property Distribution"
)

fig.update_layout(
    title_x=0.5,  # Center title
    xaxis_title="Property Type",
    yaxis_title='count',
    font = dict(size= 16),
    height=500, 
    width=1200
)

fig.show()

#  Suburban Property Distribution
import plotly.io as pio
propertyType = house_rent["suburbName_clean"].value_counts().reset_index()
propertyType.columns = ['Suburban Name', 'count']

fig = px.pie(
    propertyType, 
    names='Suburban Name', 
    values='count', 
    color_discrete_sequence=px.colors.qualitative.Vivid, 
    title="Property Distribution",
)

fig.update_layout(
    title_x=0.5,  # Center title
    title_font=dict(size=24),
    height=500, 
    width=1200
)

fig.show()

#  Geographic Distribution of Rental Listings
import plotly.io as pio
pio.renderers.default = "notebook"
fig1 = px.scatter(house_rent,x="longitude", y="latitude")
fig1.show()

#  Rental Property Distribution on Delhi Map
import matplotlib.image as mpimg

Delhi_img = mpimg.imread("Delhi.jpg")  

ax = house_rent.plot(kind="scatter", x="longitude", y="latitude",
                      colorbar=False, alpha=0.5)

plt.gca().set_facecolor('black')

plt.imshow(Delhi_img, extent=[76.85, 77.41, 28.41, 28.9], alpha=0.6)

plt.show()

# Distribution of House Sizes (in sq ft)
import plotly.io as pio
fig = px.histogram(
    house_rent, 
    x="size_sq_ft", 
    color_discrete_sequence=['yellow'],
)

fig.update_layout(
    title="Distribution of Size (sq ft)",
    xaxis_title="Size (sq ft)",
    yaxis_title="Count",
    title_x=0.5  # Center the title
)

fig.show()

# Create a price category column for stratification
house_rent["size_cat"] = pd.cut(house_rent["size_sq_ft"],
                               bins=[0,500,1000,1500,2000,np.inf],
                               labels=[1,2,3,4,5])

# House Size Category Distribution
import plotly.io as pio
fig = px.histogram(
    house_rent, 
    x="size_cat", 
    color="size_cat",  # Ensure color categories are applied correctly
    color_discrete_sequence=["red", "blue", "green", "purple", "orange"]
)

fig.show()

# We drop longitude and latitude feature more convenience
house_rent = house_rent.drop('latitude',axis=1)
house_rent = house_rent.drop('longitude',axis=1)

house_rent = house_rent.reset_index(drop=True)

# Perform stratified train-test split
split = StratifiedShuffleSplit(n_splits=1, test_size=0.2, random_state=42)
for train_index, test_index in split.split(house_rent, house_rent["size_cat"]):
    train_set = house_rent.loc[train_index]
    test_set = house_rent.loc[test_index]

print("Training set size:", train_set.shape)
print("Testing set size:", test_set.shape)

Training set size: (12723, 10)
Testing set size: (3181, 10)

train_set.head()

test_set.head()

house_rent["size_cat"].value_counts(normalize=True)

size_cat
2    0.450578
1    0.194982
3    0.172032
4    0.158011
5    0.024396
Name: proportion, dtype: float64

train_set["size_cat"].value_counts(normalize=True)

size_cat
2    0.450601
1    0.195001
3    0.172051
4    0.157982
5    0.024365
Name: proportion, dtype: float64

test_set["size_cat"].value_counts(normalize=True)

size_cat
2    0.450487
1    0.194907
3    0.171959
4    0.158126
5    0.024521
Name: proportion, dtype: float64

for set_ in (train_set,test_set):
    set_.drop("size_cat",axis=1,inplace=True)

# Prepare training data
X_train = train_set.drop("price", axis=1)
y_train = train_set["price"]

num_attribs = list(X_train.select_dtypes(include=["number"]))
cat_attribs = ["propertyType","suburbName_clean" ]

# Create column transformer
full_pipeline = ColumnTransformer([
    ("num", StandardScaler(), num_attribs),
    ("cat", OneHotEncoder(handle_unknown='ignore', sparse_output=False), cat_attribs)
])

X_train.shape

(12723, 8)

X_train_prepared = full_pipeline.fit_transform(X_train)

X_test = test_set.drop("price", axis=1)
y_test = test_set["price"]

X_test_prepared = full_pipeline.transform(X_test)

X_train_prepared

array([[-0.37198282, -0.01166857,  0.65636707, ...,  0.        ,
         0.        ,  0.        ],
       [ 0.03138368, -0.01166857,  0.58602418, ...,  0.        ,
         0.        ,  0.        ],
       [ 0.03138368, -1.19934185,  1.46024139, ...,  0.        ,
         0.        ,  0.        ],
       ...,
       [-0.77534932, -1.19934185, -0.1261086 , ...,  0.        ,
         0.        ,  0.        ],
       [ 0.03138368, -0.01166857,  1.00229333, ...,  0.        ,
         0.        ,  0.        ],
       [ 0.03138368, -0.01166857, -0.18139006, ...,  1.        ,
         0.        ,  0.        ]])

from sklearn.ensemble import RandomForestRegressor

rf = RandomForestRegressor(random_state=42)

param_dist = {
    'n_estimators': [100, 200, 300, 400],
    'max_depth': [10, 20, 30, None],
    'min_samples_split': [2, 5, 10],
    'min_samples_leaf': [1, 2, 4],
    'max_features': ['sqrt', 'log2']
}

random_search = RandomizedSearchCV(
    estimator=rf,
    param_distributions=param_dist,
    n_iter=30,           
    cv=5,                
    verbose=2,
    n_jobs=-1,
    scoring='r2',
    random_state=42
)

random_search.fit(X_train_prepared, y_train)

print("Best Params:", random_search.best_params_)

best_model = random_search.best_estimator_
y_pred = best_model.predict(X_test_prepared)
print("MAE:", mean_absolute_error(y_test, y_pred))
print("R²:", r2_score(y_test, y_pred))

Fitting 5 folds for each of 30 candidates, totalling 150 fits
Best Params: {'n_estimators': 400, 'min_samples_split': 2, 'min_samples_leaf': 2, 'max_features': 'log2', 'max_depth': None}
MAE: 3369.0222959375624
R²: 0.8218728583717225

# Randomforest regressor
model = RandomForestRegressor(n_estimators=  400, min_samples_split= 2, min_samples_leaf =2, max_features= 'log2')
model.fit(X_train_prepared, y_train)

y_pred = model.predict(X_test_prepared)

mae = mean_absolute_error(y_test, y_pred)
r2 = r2_score(y_test, y_pred)

print(f"Mean Absolute Error: {mae:.2f}")
print(f"R² Score: {r2:.2f}")

Mean Absolute Error: 3372.42
R² Score: 0.82

from xgboost import XGBRegressor

xgb_model = XGBRegressor(n_estimators=150, max_depth=10, learning_rate=0.1, random_state=42)
xgb_model.fit(X_train_prepared, y_train)

y_pred_xgb = xgb_model.predict(X_test_prepared)

print("XGBoost MAE:", mean_absolute_error(y_test, y_pred_xgb))
print("XGBoost R²:", r2_score(y_test, y_pred_xgb))

XGBoost MAE: 3420.8210403168964
XGBoost R²: 0.8099862379060654

from lightgbm import LGBMRegressor

lgb_model = LGBMRegressor(n_estimators=150, max_depth=10, learning_rate=0.1, random_state=42)
lgb_model.fit(X_train_prepared, y_train)

y_pred_lgb = lgb_model.predict(X_test_prepared)

print("LightGBM MAE:", mean_absolute_error(y_test, y_pred_lgb))
print("LightGBM R²:", r2_score(y_test, y_pred_lgb))

[LightGBM] [Info] Auto-choosing col-wise multi-threading, the overhead of testing was 0.000820 seconds.
You can set `force_col_wise=true` to remove the overhead.
[LightGBM] [Info] Total Bins 737
[LightGBM] [Info] Number of data points in the train set: 12723, number of used features: 15
[LightGBM] [Info] Start training from score 21841.225026
[LightGBM] [Warning] No further splits with positive gain, best gain: -inf
[LightGBM] [Warning] No further splits with positive gain, best gain: -inf
[LightGBM] [Warning] No further splits with positive gain, best gain: -inf
[LightGBM] [Warning] No further splits with positive gain, best gain: -inf
LightGBM MAE: 3420.458390342412
LightGBM R²: 0.8207300652203096

from catboost import CatBoostRegressor

cat_model = CatBoostRegressor(iterations=300, depth=10, learning_rate=0.1, verbose=0)
cat_model.fit(X_train_prepared, y_train)

y_pred_cat = cat_model.predict(X_test_prepared)

print("CatBoost MAE:", mean_absolute_error(y_test, y_pred_cat))
print("CatBoost R²:", r2_score(y_test, y_pred_cat))

CatBoost MAE: 3398.996688811509
CatBoost R²: 0.8213430526692512

my_model =model

import joblib

# Save the model
joblib.dump(my_model, "house_price_model.pkl")

print("Model saved successfully!")

Model saved successfully!

my_model_loaded = joblib.load("house_price_model.pkl") # DIFF

# let's try the full preprocessing pipeline on a few training instances
some_data = house_rent.iloc[:5]
some_labels = y_train.iloc[:5]
some_data_prepared = full_pipeline.transform(some_data)

print("Predictions:", model.predict(some_data_prepared))

Predictions: [ 9697.23877809 23381.70283698 33055.84970388 27836.59551783
 11366.20807406]

print("Labels:", list(some_labels))

Labels: [12000, 22000, 15000, 17000, 22000]

# Create the mapping from locality name to its encoded value
locality_encoding_map = house_rent.groupby("localityName_clean")["locality_encoded"].first().to_dict()

# This function converts the user's locality name into 
# its corresponding encoded value (mean price), preparing 
# the input for the rent prediction model.

def prepare_input_with_locality_name(user_input_dict):
    # Convert locality name to lowercase
    loc_clean = user_input_dict["localityName"].lower().strip()


    encoded_val = locality_encoding_map.get(loc_clean)

    if encoded_val is None:
        raise ValueError(f"❌ Unknown locality: {loc_clean}. Please check spelling.")

    user_input_dict["locality_encoded"] = encoded_val
    user_input_dict.pop("localityName")  

    return pd.DataFrame([user_input_dict])

user_input = {
    "size_sq_ft":500,
    "propertyType": "independent floor",
    "bedrooms": 2,
    "localityName": "geeta colony",
    "suburbName_clean": "east delhi",
    "AP_dist_km": 20,

}
new_data = prepare_input_with_locality_name(user_input)
new_data_prepared = full_pipeline.transform(new_data)
predicted_price = model.predict(new_data_prepared)

print(f"🏠 Predicted Rent: ₹{predicted_price[0]:,.2f}")

🏠 Predicted Rent: ₹10,997.24

	Column1	size_sq_ft	propertyType	bedrooms	latitude	longitude	localityName	suburbName	cityName	price	companyName	closest_mtero_station_km	AP_dist_km	Aiims_dist_km	NDRLW_dist_km
0	0	400	Independent Floor	1	28.641010	77.284386	Swasthya Vihar	Delhi East	Delhi	9000	Dream Homez	0.577495	21.741188	11.119239	6.227231
1	1	1050	Apartment	2	28.594969	77.298668	mayur vihar phase 1	Delhi East	Delhi	20000	Rupak Properties Stock	0.417142	21.401856	9.419061	9.217502
2	2	2250	Independent Floor	2	28.641806	77.293922	Swasthya Vihar	Delhi East	Delhi	28000	Aashiyana Real Estate	0.125136	22.620365	11.829486	7.159184
3	3	1350	Independent Floor	2	28.644363	77.293228	Krishna Nagar	Delhi East	Delhi	28000	Shivam Real Estate	0.371709	22.681201	11.982708	7.097348
4	4	450	Apartment	2	28.594736	77.311150	New Ashok Nagar	Delhi East	Delhi	12500	Shree Properties	1.087760	22.592810	10.571573	10.263271

	Column1	size_sq_ft	bedrooms	latitude	longitude	price	closest_mtero_station_km	AP_dist_km	Aiims_dist_km	NDRLW_dist_km
count	17890.000000	17890.000000	17890.000000	17890.000000	17890.000000	1.789000e+04	17890.000000	17890.000000	17890.000000	17890.000000
mean	8944.500000	1176.342091	2.168865	28.609382	77.168368	3.345196e+04	0.931495	13.727784	11.238134	11.421994
std	5164.542493	873.751044	0.971414	0.099547	0.097611	8.802054e+04	8.287856	11.357063	11.167202	11.063323
min	0.000000	100.000000	1.000000	19.185120	73.213829	1.200000e+03	0.000692	1.784779	0.634508	0.722023
25%	4472.250000	620.000000	1.000000	28.562540	77.103718	1.350000e+04	0.457782	11.018715	7.769267	7.986813
50%	8944.500000	900.000000	2.000000	28.611803	77.168755	2.200000e+04	0.698560	13.184035	10.515524	11.015571
75%	13416.750000	1600.000000	3.000000	28.651593	77.224998	3.500000e+04	1.087740	17.163502	15.514042	15.192483
max	17889.000000	16521.000000	15.000000	28.872597	80.358467	5.885646e+06	1096.479453	1109.894053	1115.621439	1123.778457

	size_sq_ft	propertyType	bedrooms	latitude	longitude	cityName	price	AP_dist_km	localityName_clean	locality_encoded	suburbName_clean
0	400	Independent Floor	1	28.641010	77.284386	Delhi	9000	21.741188	swasthya vihar	22251.162791	east delhi
1	1050	Apartment	2	28.594969	77.298668	Delhi	20000	21.401856	mayur vihar phase 1	14065.000000	east delhi
2	2250	Independent Floor	2	28.641806	77.293922	Delhi	28000	22.620365	swasthya vihar	22251.162791	east delhi
3	1350	Independent Floor	2	28.644363	77.293228	Delhi	28000	22.681201	krishna nagar	20858.333333	east delhi
4	450	Apartment	2	28.594736	77.311150	Delhi	12500	22.592810	new ashok nagar	9664.009112	east delhi

	size_sq_ft	propertyType	bedrooms	cityName	price	AP_dist_km	localityName_clean	locality_encoded	suburbName_clean	size_cat
11091	654	Independent Floor	1	Delhi	13000	13.278257	patel nagar	19473.086620	delhi central	2
6700	1800	Independent Floor	3	Delhi	40000	13.186740	paschim vihar	25747.144457	west delhi	4
10251	1050	Independent Floor	2	Delhi	10500	4.129440	palam	21148.214286	south west delhi	3
10886	485	Independent Floor	1	Delhi	16500	12.665641	patel nagar	19473.086620	delhi central	1
13443	1050	Independent Floor	2	Delhi	19000	17.256704	sector-7 rohini	18853.846154	north west delhi	3

🔍 Uncover the Hidden Patterns in Delhi's Real Estate Market¶

Powered by Machine Learning, Data Visualization & Dashboarding¶

📦 Dataset Overview¶

🏠 House Features¶

📍 Location Features¶

💰 Rental Information¶

🏢 Agency Details¶

🗺️ Proximity to Key Landmarks (Geodesic distance only)¶

📁 1. Data Loading & Exploration¶

📊 3. Exploratory Data Analysis (EDA)¶

🧹 2. Data Cleaning¶

🧹 Data Cleaning Summary¶

Looking for Correlations¶

Discover and Visualize the Data to Gain Insights¶

🤖 4. Feature Selection & Modeling¶

Create a Test Set¶

Prepare the Data for Machine Learning Algorithms¶

Tuning RandomForestRegressor with RandomizedSearchCV¶

Try different models¶

📈 5. Model Evaluation Summary¶

🌲 Random Forest Regressor achieved the highest performance with an impressive R² score of 82% on the test set.¶

📦 This model has been saved for future rent price prediction tasks.¶

📉 6. Prediction¶

	size_sq_ft	propertyType	bedrooms	cityName	price	AP_dist_km	localityName_clean	locality_encoded	suburbName_clean	size_cat
15292	800	Apartment	2	Delhi	12000	17.273620	sri niwaspuri	15000.000000	other	2
15089	1000	Apartment	2	Delhi	22000	16.885609	hari nagar ashram	26500.000000	other	2
1827	1000	Independent Floor	1	Delhi	15000	21.707782	mayur vihar	19485.046729	east delhi	2
3663	1200	Independent Floor	3	Delhi	17000	11.820051	chattarpur	15355.663825	south delhi	3
5897	1400	Apartment	2	Delhi	22000	12.627945	paschim vihar	25747.144457	west delhi	3